Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews)
Objective Today, people face different decision-making criteria when purchasing products and services. One of these criteria is using the reviews of the previous purchasers of products and services. A large volume of reviews is seen as a challenge for these people. The present study aimed to create...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
University of Tehran
2022-12-01
|
| Series: | مدیریت بازرگانی |
| Subjects: | |
| Online Access: | https://jibm.ut.ac.ir/article_90594_e4b76ad7f079c3ad7bbc3b0f429e7c1d.pdf |
| _version_ | 1828012167422541824 |
|---|---|
| author | Parham Parnian |
| author_facet | Parham Parnian |
| author_sort | Parham Parnian |
| collection | DOAJ |
| description | Objective
Today, people face different decision-making criteria when purchasing products and services. One of these criteria is using the reviews of the previous purchasers of products and services. A large volume of reviews is seen as a challenge for these people. The present study aimed to create a model to analyze users’ sentiments and to classify their reviews to solve the mentioned challenge.
Methodology
The present study investigated the buyers’ reviews of mobile phones purchased on the Digikala Website from 2015 to 2016. To analyze the sentiments, and to classify the reviews, deep learning-based algorithms, and convolutional networks, subtypes of deep networks, were suggested. Prior to preprocessing and homogenizing the data, the study used a pre-trained Fastext model to convert the words into integer vectors and deliver them as inputs to the proposed deep network.
Findings
To train the selected model, the training algorithm was carried out on it 90 times. To validate the performance of the selected model, confusion matrix, accuracy, recall, F1-score, and precision rate criteria were used.
Conclusion
The present study used the deep networks approach, convolutional networks, and bidirectional long short-term memory to classify the buyers’ reviews of the mobile phone from the website above at 93% accuracy, and after 90 training periods. |
| first_indexed | 2024-04-10T09:29:42Z |
| format | Article |
| id | doaj.art-3968f7ad8a8740929fa0886d1885bb00 |
| institution | Directory Open Access Journal |
| issn | 2008-5907 2423-5091 |
| language | fas |
| last_indexed | 2024-04-10T09:29:42Z |
| publishDate | 2022-12-01 |
| publisher | University of Tehran |
| record_format | Article |
| series | مدیریت بازرگانی |
| spelling | doaj.art-3968f7ad8a8740929fa0886d1885bb002023-02-19T06:41:24ZfasUniversity of Tehranمدیریت بازرگانی2008-59072423-50912022-12-0114467569410.22059/jibm.2022.334338.425590594Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews)Parham Parnian0Msc. Student, Department of Computer Engineering, Faculty of Computer Engineering, Shahid Bahonar University of Kerman, Kerman, Iran.Objective Today, people face different decision-making criteria when purchasing products and services. One of these criteria is using the reviews of the previous purchasers of products and services. A large volume of reviews is seen as a challenge for these people. The present study aimed to create a model to analyze users’ sentiments and to classify their reviews to solve the mentioned challenge. Methodology The present study investigated the buyers’ reviews of mobile phones purchased on the Digikala Website from 2015 to 2016. To analyze the sentiments, and to classify the reviews, deep learning-based algorithms, and convolutional networks, subtypes of deep networks, were suggested. Prior to preprocessing and homogenizing the data, the study used a pre-trained Fastext model to convert the words into integer vectors and deliver them as inputs to the proposed deep network. Findings To train the selected model, the training algorithm was carried out on it 90 times. To validate the performance of the selected model, confusion matrix, accuracy, recall, F1-score, and precision rate criteria were used. Conclusion The present study used the deep networks approach, convolutional networks, and bidirectional long short-term memory to classify the buyers’ reviews of the mobile phone from the website above at 93% accuracy, and after 90 training periods.https://jibm.ut.ac.ir/article_90594_e4b76ad7f079c3ad7bbc3b0f429e7c1d.pdfdeep learningconvolutional neural networksreviews classificationtext mining |
| spellingShingle | Parham Parnian Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews) مدیریت بازرگانی deep learning convolutional neural networks reviews classification text mining |
| title | Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews) |
| title_full | Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews) |
| title_fullStr | Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews) |
| title_full_unstemmed | Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews) |
| title_short | Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews) |
| title_sort | customer reviews classification with text mining and deep learning approach case study digikala customers reviews |
| topic | deep learning convolutional neural networks reviews classification text mining |
| url | https://jibm.ut.ac.ir/article_90594_e4b76ad7f079c3ad7bbc3b0f429e7c1d.pdf |
| work_keys_str_mv | AT parhamparnian customerreviewsclassificationwithtextmininganddeeplearningapproachcasestudydigikalacustomersreviews |